indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Podcast processing for youtube feeds

merge-requests/30/head
Bob Mottram 2022-01-14 17:40:42 +00:00
parent 75a21345cc
commit 6cceef2386
1 changed files with 20 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
newswire.py
View File

@ -501,7 +501,7 @@ def xml_podcast_to_dict(xml_item: str, xml_str: str) -> {}:
# get the image for the podcast, if it exists # get the image for the podcast, if it exists
podcast_episode_image = None podcast_episode_image = None
episode_image_tags = ['<itunes:image'] episode_image_tags = ['<itunes:image', '<media:thumbnail']
for image_tag in episode_image_tags: for image_tag in episode_image_tags:
item_str = xml_item item_str = xml_item
if image_tag not in xml_item: if image_tag not in xml_item:
@ -516,6 +516,12 @@ def xml_podcast_to_dict(xml_item: str, xml_str: str) -> {}:
episode_image = episode_image.split('"')[0] episode_image = episode_image.split('"')[0]
podcast_episode_image = episode_image podcast_episode_image = episode_image
break break
elif 'url="' in episode_image:
episode_image = episode_image.split('url="')[1]
if '"' in episode_image:
episode_image = episode_image.split('"')[0]
podcast_episode_image = episode_image
break
else: else:
if '>' in episode_image: if '>' in episode_image:
episode_image = episode_image.split('>')[1] episode_image = episode_image.split('>')[1]
@ -1019,9 +1025,15 @@ def _atom_feed_yt_to_dict(base_dir: str, domain: str, xml_str: str,
description = atom_item.split('<summary>')[1] description = atom_item.split('<summary>')[1]
description = description.split('</summary>')[0] description = description.split('</summary>')[0]
description = remove_html(description) description = remove_html(description)
link = atom_item.split('<yt:videoId>')[1]
link = link.split('</yt:videoId>')[0] link, link_mime_type = get_link_from_rss_item(atom_item)
link = 'https://www.youtube.com/watch?v=' + link.strip() if not link:
link = atom_item.split('<yt:videoId>')[1]
link = link.split('</yt:videoId>')[0]
link = 'https://www.youtube.com/watch?v=' + link.strip()
if not link:
continue
pub_date = atom_item.split('<published>')[1] pub_date = atom_item.split('<published>')[1]
pub_date = pub_date.split('</published>')[0] pub_date = pub_date.split('</published>')[0]
@ -1030,13 +1042,16 @@ def _atom_feed_yt_to_dict(base_dir: str, domain: str, xml_str: str,
if _valid_feed_date(pub_date_str): if _valid_feed_date(pub_date_str):
post_filename = '' post_filename = ''
votes_status = [] votes_status = []
podcast_properties = xml_podcast_to_dict(atom_item, xml_str)
if podcast_properties:
podcast_properties['linkMimeType'] = link_mime_type
_add_newswire_dict_entry(base_dir, domain, _add_newswire_dict_entry(base_dir, domain,
result, pub_date_str, result, pub_date_str,
title, link, title, link,
votes_status, post_filename, votes_status, post_filename,
description, moderated, mirrored, description, moderated, mirrored,
[], 32, session, debug, [], 32, session, debug,
None) podcast_properties)
post_ctr += 1 post_ctr += 1
if post_ctr >= max_posts_per_source: if post_ctr >= max_posts_per_source:
break break